Landslide identification using machine learning techniques: Review, motivation, and future prospects

Sreelakshmi, S.; S, Vinod Chandra S; Shaji, E.

doi:10.1007/s12145-022-00889-2

Cited by 23 publications

(6 citation statements)

References 145 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL architectures are regularly used to produce landslide inventories in space and time (Bhuyan et al, 2023, Novellino et al, 2024 while discriminating between landslide types (Rana et al, 2023) and the likely trigger (Rana et al, 2021). These tools are also frequently published openly to promote the benchmarking against same procedures in a consistent manner (Amateya et al, 2021;Das et al, 2023;Rana et al, 2022), thus encouraging the adoption and enhancement of the developed approaches.…”

Section: Discussionmentioning

confidence: 99%

An ensemble neural network approach for space-time landslide predictive modelling

Lim,

Santinelli,

Dahal

et al. 2024

Preprint

View full text Add to dashboard Cite

There is an urgent need for accurate and effective Landslide Early Warning Systems (LEWS). Most LEWS are currently based on a single temporally-aggregated measure of rainfall derived from either in-situ measurements or satellite-based rainfall estimates. Relying on a summary metric of precipitation may not capture the complexity of the rainfall signal and its dynamics in space and time in triggering landslides. Here, we present a proof-of-concept for constructing a LEWS that is based on an integrated spatio-temporal modelling framework. Our proposed methodology builds upon a recent approach that uses a daily rainfall time series instead of the traditional cumulated scalar approximation. Specifically, we partition the study area into slope units and use a Gated Recurrent Unit (GRU) to process a satellite-derived rainfall time series and combine the output features with a second neural network (NN) tasked with capturing the effect of terrain characteristics. To assess if our approach enhances accuracy, we applied it in Vietnam and compared it against a standard modelling approach that incorporates terrain characteristics and cumulative rainfall over 14 days. Our protocol leads to better performance in hindcasting landslides when using past rainfall estimates (CHIRPS), as compared to the standard modelling approach. While not tested here, our approach can be extended to rainfall obtained from weather forecasts, potentially leading to actual landslide forecasts.

show abstract

Section: Discussionmentioning

confidence: 99%

An ensemble neural network approach for space-time landslide predictive modelling

Lim,

Santinelli,

Dahal

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In the past few years, there has been an upward pattern in the application of ML techniques, for instance, support vector machines (SVMs) for identifying landslide-prone locations [15][16][17], logistic model trees (LMTs) [18,19], artificial neural networks (ANNs) [20][21][22], and decision trees (DTs) [23][24][25]. Most scholars claim that ML techniques are comparatively more efficient and effective than conventional approaches.…”

Section: Introductionmentioning

confidence: 99%

Integrating Machine Learning Ensembles for Landslide Susceptibility Mapping in Northern Pakistan

Ali,

Chen,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Natural disasters, notably landslides, pose significant threats to communities and infrastructure. Landslide susceptibility mapping (LSM) has been globally deemed as an effective tool to mitigate such threats. In this regard, this study considers the northern region of Pakistan, which is primarily susceptible to landslides amid rugged topography, frequent seismic events, and seasonal rainfall, to carry out LSM. To achieve this goal, this study pioneered the fusion of baseline models (logistic regression (LR), K-nearest neighbors (KNN), and support vector machine (SVM)) with ensembled algorithms (Cascade Generalization (CG), random forest (RF), Light Gradient-Boosting Machine (LightGBM), AdaBoost, Dagging, and XGBoost). With a dataset comprising 228 landslide inventory maps, this study employed a random forest classifier and a correlation-based feature selection (CFS) approach to identify the twelve most significant parameters instigating landslides. The evaluated parameters included slope angle, elevation, aspect, geological features, and proximity to faults, roads, and streams, and slope was revealed as the primary factor influencing landslide distribution, followed by aspect and rainfall with a minute margin. The models, validated with an AUC of 0.784, ACC of 0.912, and K of 0.394 for logistic regression (LR), as well as an AUC of 0.907, ACC of 0.927, and K of 0.620 for XGBoost, highlight the practical effectiveness and potency of LSM. The results revealed the superior performance of LR among the baseline models and XGBoost among the ensembles, which contributed to the development of precise LSM for the study area. LSM may serve as a valuable tool for guiding precise risk-mitigation strategies and policies in geohazard-prone regions at national and global scales.

show abstract

“…As shown in Figure 1, the uniform deformation stage is the main stage of early identification. Facts have proved that scientific and reasonable early potential disaster identification can effectively avoid the occurrence of landslide disasters or reduce losses to a large extent (Sreelakshmi et al, 2022). For example, He et al (2005) determine the role and correlation of the main dynamic factors, and compared with the actual dynamic pattern of Xintan landslide, showing that it coincides with the actual slip mode and formation mechanism of Xintan landslide.…”

Section: Introductionmentioning

confidence: 99%

Review article: Research progress on influencing factors, data, and methods for early identification of landslide hazards

Lu,

Yang,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. The early identification of potential landslide hazards has always been a hot and difficult issue in the field of international landslide research. In recent years, many scholars have conducted extensive and beneficial explorations in this field, making significant contributions to the effective prevention of landslide disasters. However, until now, there are very few review documents on summarizing such valuable experience in the system, which makes it difficult to meet the ever-increasing demand of researchers in scientific documents. To address the gap, this paper systematically reviews 843 documents collected by the two data platforms of Web of Science (WOS) and Scopus from 1971 to 2023 by using the bibliometric analysis software. This paper first figures out the internal relationship between documents by analysing their spatial and temporal distribution characteristics, and then emphatically analyses the application, advantages and disadvantages of different early identification methods based on the influencing factors of landslide disaster formation and multi-source data acquisition links. And finally, this paper discusses the challenges and development trends in this field from four aspects of cooperative analysis, multi-source data, topic analysis and research trends, and puts forward some suggestions. This research can help researchers to use various early identification methods reasonably and provide summary and integration services of scientific document achievements for efficient research in this field.

show abstract

Landslide identification using machine learning techniques: Review, motivation, and future prospects

Cited by 23 publications

References 145 publications

An ensemble neural network approach for space-time landslide predictive modelling

An ensemble neural network approach for space-time landslide predictive modelling

Integrating Machine Learning Ensembles for Landslide Susceptibility Mapping in Northern Pakistan

Review article: Research progress on influencing factors, data, and methods for early identification of landslide hazards

Contact Info

Product

Resources

About